Formal neural network specification and its implications on standardization

作者: Georg Dorffner , Herbert Wiklicky , Erich Prem

DOI: 10.1016/S0920-5489(98)00069-5

关键词: Formal specificationArtificial neural networkStandardizationComputer scienceConnectionismSystems architectureArtificial intelligenceImpossibilityFormal description

摘要: This paper introduces a formal framework for describing and specifying neural networks discusses several important issues with implications network standardization. In particular, definition two tools graphical description specification are introduced. Issues such as the theoretical impossibility of canonical description, or need complete (including global algorithms) discussed. Several examples, making use developed tools, illustrate these discussions. summary, this aims at contributing to endeavour standardization both practically theoretically.

参考文章(17)
David Lowe, David S. Broomhead, Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks Complex Systems. ,vol. 2, pp. 321- 355 ,(1988)
Herbert Wiklicky, Thierry Denœux, Alberto Lafuente, Javier Olarte, Santiago Rementeria, Veerle Walravens, A Tripartite Framework for Artificial Neural Networks international conference on artificial neural networks. pp. 1031- 1034 ,(1992) , 10.1016/B978-0-444-89488-5.50042-7
David E. Rumelhart, James L. McClelland, , Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations Computational Models of Cognition and Perception. ,(1986) , 10.7551/MITPRESS/5236.001.0001
Imtiaz A. Pirbhai, Derek J. Hatley, Strategies for Real-Time System Specification ,(1987)
R. M. Golden, A unified framework for connectionist systems. Biological Cybernetics. ,vol. 59, pp. 109- 120 ,(1988) , 10.1007/BF00317773
Robinson, Niranjan, Fallside, Generalising the nodes of the error propagation network international joint conference on neural network. pp. 583- ,(1989) , 10.1109/IJCNN.1989.118343
Suresh Mangrulkar, Artificial neural systems. Isa Transactions. ,vol. 29, pp. 5- 7 ,(1990) , 10.1016/0019-0578(90)90024-F
L. Bottou, P. Gallinari, A unified formalism for neural net training algorithms international joint conference on neural network. ,vol. 4, pp. 7- 12 ,(1992) , 10.1109/IJCNN.1992.227347